Research map / Vision-language and multimodal / Cross-modal learning
Cancer Survival Prediction by Cyclic Generation and Multi-grained Alignment
Yongqi Bu, Qinggang Niu, Zhen Li, Yanyu Xu, Jun Wang, Guoxian Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use CIMA instead of best genomics-only baseline SNNTrans | CIMA · TCGA, five cancers | C-index: 7.2% | Improved |
| use CIMA instead of best WSI-only baseline WiKG | CIMA · TCGA, five cancers | C-index: 3.8% | Improved |
| use CIMA instead of best multimodal baseline PIBD | CIMA · TCGA, five cancers | C-index: 1.4% | Improved |
| use CIMA instead of best incomplete-multimodal baseline DCP | CIMA · TCGA, five cancers | C-index: 2.5% | Improved |
| use CIMA instead of DCP on STAD | CIMA · TCGA STAD (complete multimodal) | C-index: .595±.022 -> .585±.013 | Hurt |
| use CIMA instead of SurvPath on COADREAD | CIMA · TCGA COADREAD (complete multimodal) | C-index: .607±.014 -> .622±.013 | Improved |
| raise genomics missing rate from 0.25 to 0.9 for multimodal baselines | multimodal baselines · TCGA STAD, masked genomics | C-index | Hurt |
| use cyclic modality reconstruction under high genomics missingness | CIMA · TCGA STAD, masked genomics | C-index | Improved |
| raise genomics missing rate above 75% for multimodal baselines vs unimodal | multimodal baselines · TCGA STAD, masked genomics | C-index | Hurt |
Closest papers by meaning
- Multimodal Prototyping for cancer survival prediction (ICML 2024 · similarity 0.88)
- Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction (ICLR 2024 · similarity 0.87)
- Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction (CVPR 2024 · similarity 0.86)
- CA-MLIF: Cross-Attention and Multimodal Low-Rank Interaction Fusion Framework for Tumor Prognostic Prediction (AAAI 2025 · similarity 0.85)
- HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data (NeurIPS 2024 · similarity 0.84)
- When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
